January 22, 2026

Airtable to Instagram, posts publish with AI edits

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

Your Instagram pipeline probably breaks in the same place every time. Someone drops an image into Airtable, someone else “quickly” edits it, the caption lives in a doc somewhere, and posting happens when a human remembers.

This hits social media managers hardest, but content creators and marketing leads feel it too. Airtable Instagram automation turns that messy handoff into a repeatable system that publishes on time, with fewer mistakes.

This workflow takes an Airtable image, uses AI to analyze and improve it, then posts the finished version to Instagram while keeping your Airtable status updated. You’ll see what it does, what you need, and where teams usually get stuck.

How This Automation Works

The full n8n workflow, from trigger to final output:

n8n Workflow Template: Airtable to Instagram, posts publish with AI edits

Click to explore

flowchart LR

    subgraph sg0["Analyze image Flow"]
        direction LR
        n0["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/webhook.dark.svg' width='40' height='40' /></div><br/>Webhook"]
        n1["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Airtable Upload"]
        n2["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/airtable.svg' width='40' height='40' /></div><br/>Status Complete"]
        n3["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/airtable.svg' width='40' height='40' /></div><br/>Status Error"]
        n4@{ icon: "mdi:robot", form: "rounded", label: "Analyze image", pos: "b", h: 48 }
        n5@{ icon: "mdi:brain", form: "rounded", label: "OpenAI Chat Model", pos: "b", h: 48 }
        n6["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Create Media Container"]
        n7["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Publish Media"]
        n8["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/airtable.svg' width='40' height='40' /></div><br/>Get Image"]
        n9["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/airtable.svg' width='40' height='40' /></div><br/>Get Rows"]
        n10@{ icon: "mdi:robot", form: "rounded", label: "Prompt Optimization", pos: "b", h: 48 }
        n11["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Nano Bannana Image Generation"]
        n0 --> n8
        n9 --> n10
        n8 --> n4
        n4 --> n9
        n7 --> n2
        n5 -.-> n10
        n10 --> n11
        n6 --> n7
        n11 --> n1
        n11 --> n6
        n11 --> n3
    end

    %% Styling
    classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
    classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
    classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
    classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
    classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
    classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
    classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
    classDef disabled stroke-dasharray: 5 5,opacity: 0.5
    class n4,n10 ai
    class n5 aiModel
    class n2,n3,n8,n9 database
    class n0,n1,n6,n7,n11 api
    classDef customIcon fill:none,stroke:none
    class n0,n1,n2,n3,n6,n7,n8,n9,n11 customIcon

The Problem: Instagram posting gets messy fast

Posting consistently sounds simple until you try to do it at scale. Images sit in Airtable with “almost ready” statuses for days. Edits happen in a rush, so you lose track of which file is the final one, and someone inevitably posts the wrong version. Then there’s the mental load: checking dimensions, rewriting captions, chasing approvals, and copying assets into Meta tools. None of this is creative work, but it still eats the afternoon. Honestly, it’s the kind of busywork that makes teams stop posting altogether.

The friction compounds. Here’s where it breaks down most often:

You spend about 10–20 minutes per post hunting files, making a “quick edit,” and exporting the right format.
Versions multiply, so the wrong image or caption gets published, and you only notice after it’s live.
Status tracking becomes a lie, because nobody updates Airtable the moment something changes.
Even with scheduling tools, you still have to manually prep the creative, which is where most delays happen.

The Solution: Airtable images edited by AI, then posted to Instagram

This n8n workflow turns Airtable into the command center for your Instagram publishing. A webhook triggers the automation with an Airtable record ID, and the workflow fetches the source image and the creative directions your team already stored (things like composition, lighting, style, atmosphere, color palette, and text overlay). Then AI steps in twice: first it “looks” at the image using a vision model to understand what’s there, and then it refines an editing prompt based on your parameters. Google Gemini generates a new image variation from that prompt, the workflow uploads the result back into Airtable, and then posts it to Instagram using the Graph API. If posting succeeds, Airtable gets marked complete. If something fails, Airtable gets marked failed, so you see the problem immediately.

The flow is straightforward once it’s running. Airtable provides the inputs, OpenAI handles image understanding, and Gemini produces the edited variant. Finally, Meta’s Instagram Graph API publishes the post and the workflow updates status so your team stays in sync.

What You Get: Automation vs. Results

What This Workflow Automates

Results You’ll Get

It pulls the right Airtable record and downloads the attached image automatically.
It analyzes the image content with a vision model to generate a better edit prompt.
It creates a new AI-edited image variation with Gemini and uploads it back to Airtable.
It publishes to Instagram via the Graph API and updates Airtable status based on success or failure.

Most teams get about 2 hours back per week once posting becomes “set and check,” not “build and chase.”
You reduce last-minute posting mistakes because the system posts from the approved record, not someone’s desktop.
Content moves faster since status updates happen automatically and are visible in Airtable.
You get more consistent creative outputs because prompts follow the same structure every time.
Failures become obvious, which means quicker fixes and fewer missed posting windows.

Example: What This Looks Like

Say you publish 5 posts a week and each one takes about 25 minutes to prep (find the right Airtable row, export an edit, upload to Meta tools, then update status). That’s roughly 2 hours a week of repetitive work. With this workflow, you trigger it with a record ID, then wait for AI generation and posting (often around 10–20 minutes of background processing). Your hands-on time drops to a couple minutes per post, mainly for review and approval.

What You’ll Need

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Airtable to store images, fields, and status.
OpenAI API key for image analysis (get it from your OpenAI dashboard).
Google Gemini API key for image generation (get it from Google AI Studio / Google Cloud).
Meta Developer + Instagram Graph API to publish from an Instagram Business account.

Skill level: Intermediate. You won’t write code, but you will paste API keys, map Airtable fields, and test a webhook end-to-end.

Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).

How It Works

A webhook kicks things off. Your system (or you) sends a request containing an Airtable record ID, which tells the workflow exactly what to process.

Airtable provides the source image and the creative directions. The workflow pulls the attachment plus your edit fields like composition, lighting, style, atmosphere, color palette, and any text overlay notes.

AI creates an edit prompt and generates a new image. OpenAI’s vision analysis describes what’s in the image, then a prompt-refinement step shapes that into something Gemini can reliably use to produce a polished variation.

The finished asset gets uploaded and published. The workflow uploads the generated image back to Airtable, creates an Instagram media container, releases the post, and marks the Airtable status complete or failed depending on the response.

You can easily modify the edit parameters to match your brand (or even swap Instagram for another platform) based on your needs. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Webhook Trigger

Set up the webhook entry point that receives the record ID and starts the workflow.

Add the Incoming Webhook Trigger node and set Path to 12bb14d8-f9dc-4671-b5ed-10a44238f4aa.
In your calling system, send a request that includes query.recordId so the next step can fetch the Airtable record.

Step 2: Connect Airtable Data Sources

Pull the source image record and the pending rows to be processed.

Configure Fetch Source Image with ID set to {{ $json.query.recordId }}.
Credential Required: Connect your airtableTokenApi credentials in Fetch Source Image.
Configure Retrieve Pending Rows with Operation set to search and Filter By Formula to {Status} = "Create".
Credential Required: Connect your airtableTokenApi credentials in Retrieve Pending Rows.

Execution flow: Incoming Webhook Trigger → Fetch Source Image → Inspect Image Content → Retrieve Pending Rows → Refine Edit Prompt.

Step 3: Set Up Image Analysis and Prompt Refinement (AI)

Analyze the source image and generate a refined edit prompt using the OpenAI model.

Configure Inspect Image Content with Resource set to image, Operation set to analyze, and Image URLs set to {{ $json.Picture[0].url }}.
Credential Required: Connect your openAiApi credentials in Inspect Image Content.
In Refine Edit Prompt, set Prompt Type to define and Text to Prompt guidelines for the edited image: Post Description: {{ $json['Post Description'] }} Composition: {{ $json.Composition }} Lighting: {{ $json.Lighting }} Style: {{ $json.Style }} Atmosphere: {{ $json.Atmosphere }} Color Palette: {{ $json['Color Palette'] }} Text Overlay: {{ $json['Text Overlay'] }}.
Ensure OpenAI Chat Engine is connected as the language model for Refine Edit Prompt (AI sub-node). Credential Required: Connect your openAiApi credentials in OpenAI Chat Engine, not in Refine Edit Prompt.

Step 4: Generate the Edited Image and Run Parallel Outputs

Create the new image with Gemini and send the result to Airtable and the social media pipeline in parallel.

Configure Generate Banana Image with URL set to https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent and JSON Body to the provided expression (including {{ $('Fetch Source Image').item.json['Nano Image'][0].url }} for the inline image).
Credential Required: Connect your httpHeaderAuth credentials in Generate Banana Image.
Generate Banana Image outputs to both Airtable Attachment Upload and Build Media Container in parallel.
In Airtable Attachment Upload, set URL to =https://content.airtable.com/v0/appFSBG2xgidVIKR1/{{ $('Retrieve Pending Rows').item.json.id }}/Nano%20Image/uploadAttachment and JSON Body to { "contentType": "image/png", "file": "{{ $('Generate Banana Image').item.json.choices[0].message.images[0].image_url.url }}", "filename": "generated_image.png" }.
Credential Required: Connect your airtableTokenApi credentials in Airtable Attachment Upload.

⚠️ Common Pitfall: The Gemini response path {{ $('Generate Banana Image').item.json.choices[0].message.images[0].image_url.url }} must match the API response schema. Verify it by running a test execution.

Step 5: Configure Social Posting Actions

Build and publish the media post to the Facebook Graph API.

In Build Media Container, set URL to https://graph.facebook.com/v18.0/[YOUR_ID]/media and replace placeholders in the JSON Body for image_url and access_token.
In Release Media Post, set URL to https://graph.facebook.com/v18.0/[YOUR_ID]/media_publish and set creation_id to {{ $('Build Media Container').item.json.id }}.

⚠️ Common Pitfall: The [YOUR_ID] and [CONFIGURE_YOUR_TOKEN] placeholders must be replaced before activation, or publishing will fail.

Step 6: Add Error Handling and Status Updates

Update Airtable status for success or failure outcomes.

In Mark Status Complete, set Operation to update and map ID to {{ $('Retrieve Pending Rows').item.json.ID }}, with Status set to Completed.
Credential Required: Connect your airtableTokenApi credentials in Mark Status Complete.
In Mark Status Failed, set Operation to update and map Nano Image to {{ $json.error.code }} {{ $json.error.status }} with Status set to Error.
Credential Required: Connect your airtableTokenApi credentials in Mark Status Failed.

Execution flow: Release Media Post → Mark Status Complete. If Generate Banana Image errors, it routes to Mark Status Failed.

Step 7: Test and Activate Your Workflow

Validate the end-to-end process before enabling it in production.

Click Execute Workflow and send a test request to Incoming Webhook Trigger containing a valid query.recordId.
Confirm Inspect Image Content returns a structured report and Refine Edit Prompt outputs the refined prompt text.
Verify Generate Banana Image outputs an image URL and that Airtable Attachment Upload uploads the file to the Nano Image field.
Check that Build Media Container returns a creation_id and Release Media Post publishes successfully.
Ensure Airtable status updates to Completed in Mark Status Complete or Error in Mark Status Failed when failures occur.
Toggle the workflow to Active to enable production execution.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Common Gotchas

Airtable permissions matter more than people expect. If the workflow can’t fetch attachments or update Status, check the base’s sharing settings and the token scopes first.
If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.

Frequently Asked Questions

How long does it take to set up this Airtable Instagram automation automation?

Plan for about 45 minutes if you already have your API keys and Airtable fields ready.

Do I need coding skills to automate Airtable Instagram automation?

No. You’ll mostly connect accounts, paste keys, and map Airtable fields to the posting steps.

Is n8n free to use for this Airtable Instagram automation workflow?

Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in OpenAI and Gemini API costs, which are usually a few cents per image depending on prompt size and usage.

Where can I host n8n to run this automation?

Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.

Can I customize this Airtable Instagram automation workflow for carousels instead of single images?

Yes, but it takes a little work. You’d adjust your Airtable fields to store multiple attachments per record, then duplicate the “Build Media Container” logic to create a carousel container rather than a single-media container. Most teams also tweak the “Refine Edit Prompt” step so each image gets its own prompt, instead of one prompt applied everywhere. If you want a faster path, consider pairing this with your planning workflow and use a carousel-focused build like the one in your Meta posting steps.

Why is my Airtable connection failing in this workflow?

Usually it’s permissions or a changed base/table ID. Confirm the Airtable credential in n8n still has access to the base, then check the Airtable nodes that reference Base ID and Table ID. If attachments won’t download, it can also be a missing “Picture” field mapping or a record that doesn’t actually have a file attached.

How many images can this Airtable Instagram automation automation handle?

On a typical small VPS, teams run a few hundred images a day without drama, but Instagram and AI APIs can rate-limit if you push too hard.

Is this Airtable Instagram automation automation better than using Zapier or Make?

For this specific workflow, n8n is usually the better fit because you’re combining webhooks, multi-step AI processing, and error handling that benefits from branching logic. Zapier and Make can do parts of it, but the cost and complexity tend to climb once you add vision analysis, prompt refinement, retries, and “mark failed vs complete” updates back to Airtable. n8n also gives you the option to self-host, which is handy if you’re running lots of executions. If you only need “Airtable row created → post to Instagram” with no AI generation, then yes, a simpler tool can be enough. Talk to an automation expert if you’re not sure which fits.

Once this is set up, Airtable becomes your single source of truth and Instagram publishing stops being a daily scramble. The workflow handles the repetitive parts so you can spend your time on ideas, not file exports.

Need Help Setting This Up?

Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.

Lisa Granqvist

Workflow Automation Expert

Expert in workflow automation and no-code tools.

{
"id": null,
"meta": {
"instanceId": "efb0350d4d9cab8ed302cffd68fc3ae0f2b8190a6fe960bc1c3df154b46662f3"
},
"name": "Automated Image Analysis and Social Posting",
"tags": [],
"nodes": [
{
"id": "flowpast-topbar-8546",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
20,
30
],
"parameters": {
"color": 7,
"width": 1240,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "f29d992d-3607-4270-8853-e15941e28b25",
"name": "Incoming Webhook Trigger",
"type": "n8n-nodes-base.webhook",
"position": [
20,
150
],
"webhookId": "12bb14d8-f9dc-4671-b5ed-10a44238f4aa",
"parameters": {
"path": "12bb14d8-f9dc-4671-b5ed-10a44238f4aa",
"options": []
},
"typeVersion": 2.1
},
{
"id": "afba7da5-7706-427e-8854-bfe14acbad6f",
"name": "Airtable Attachment Upload",
"type": "n8n-nodes-base.httpRequest",
"position": [
470,
600
],
"parameters": {
"url": "=https://content.airtable.com/v0/appFSBG2xgidVIKR1/{{ $('Retrieve Pending Rows').item.json.id }}/Nano%20Image/uploadAttachment",
"method": "POST",
"options": [],
"jsonBody": "={\n  \"contentType\": \"image/png\",\n  \"file\": \"{{ $('Generate Banana Image').item.json.choices[0].message.images[0].image_url.url }}\",\n  \"filename\": \"generated_image.png\"\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "airtableTokenApi"
},
"credentials": {
"airtableTokenApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "42bca267-93ae-4fe7-bf6c-e9c21dc96b24",
"name": "Mark Status Complete",
"type": "n8n-nodes-base.airtable",
"position": [
1160,
590
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "appFSBG2xgidVIKR1",
"cachedResultUrl": "https://airtable.com/appFSBG2xgidVIKR1",
"cachedResultName": "Nano Banana Ad Machine"
},
"table": {
"__rl": true,
"mode": "list",
"value": "tblCzppnhEo5uVeTq",
"cachedResultUrl": "https://airtable.com/appFSBG2xgidVIKR1/tblCzppnhEo5uVeTq",
"cachedResultName": "NannoB"
},
"columns": {
"value": {
"ID": "={{ $('Retrieve Pending Rows').item.json.ID }}",
"Status": "Completed"
},
"schema": [
{
"id": "id",
"type": "string",
"display": true,
"removed": true,
"readOnly": true,
"required": false,
"displayName": "id",
"defaultMatch": true
},
{
"id": "ID",
"type": "string",
"display": true,
"removed": false,
"readOnly": true,
"required": false,
"displayName": "ID",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Picture",
"type": "array",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Picture",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Status",
"type": "options",
"display": true,
"options": [
{
"name": "Create",
"value": "Create"
},
{
"name": "Completed",
"value": "Completed"
},
{
"name": "Error",
"value": "Error"
}
],
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Status",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Core Subject",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Core Subject",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Setting",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Setting",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Composition",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Composition",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Lighting",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Lighting",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Style",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Style",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Atmosphere",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Atmosphere",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Color Palette",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Color Palette",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Text Overlay",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Text Overlay",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Nano Image",
"type": "array",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Nano Image",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Trigger n8n Workflow",
"type": "string",
"display": true,
"removed": true,
"readOnly": true,
"required": false,
"displayName": "Trigger n8n Workflow",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"ID"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "update"
},
"credentials": {
"airtableTokenApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2.1
},
{
"id": "f729f6b2-29df-46f4-a785-1e40dbd7ba91",
"name": "Mark Status Failed",
"type": "n8n-nodes-base.airtable",
"position": [
60,
610
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "appFSBG2xgidVIKR1",
"cachedResultUrl": "https://airtable.com/appFSBG2xgidVIKR1",
"cachedResultName": "Nano Banana Ad Machine"
},
"table": {
"__rl": true,
"mode": "list",
"value": "tblCzppnhEo5uVeTq",
"cachedResultUrl": "https://airtable.com/appFSBG2xgidVIKR1/tblCzppnhEo5uVeTq",
"cachedResultName": "NannoB"
},
"columns": {
"value": {
"Status": "Error",
"Nano Image": "={{ $json.error.code }} {{ $json.error.status }}"
},
"schema": [
{
"id": "id",
"type": "string",
"display": true,
"removed": false,
"readOnly": true,
"required": false,
"displayName": "id",
"defaultMatch": true
},
{
"id": "ID",
"type": "string",
"display": true,
"removed": true,
"readOnly": true,
"required": false,
"displayName": "ID",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Picture",
"type": "array",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Picture",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Status",
"type": "options",
"display": true,
"options": [
{
"name": "Create",
"value": "Create"
},
{
"name": "Completed",
"value": "Completed"
},
{
"name": "Error",
"value": "Error"
}
],
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Status",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Core Subject",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Core Subject",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Setting",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Setting",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Composition",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Composition",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Lighting",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Lighting",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Style",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Style",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Atmosphere",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Atmosphere",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Color Palette",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Color Palette",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Text Overlay",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Text Overlay",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Nano Image",
"type": "array",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Nano Image",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Trigger Workflow",
"type": "string",
"display": true,
"removed": true,
"readOnly": true,
"required": false,
"displayName": "Trigger Workflow",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "update"
},
"credentials": {
"airtableTokenApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2.1
},
{
"id": "b94d41cb-9cc6-4fb0-8dd8-0c97f6032198",
"name": "Inspect Image Content",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
510,
160
],
"parameters": {
"text": "You are an expert AI creative analyst. Your purpose is to analyze an input image and deconstruct its visual and thematic elements into a clear, structured report. Your output must be only the plain text report as described below. Do not include any conversational filler or explanatory text.\n\nBased on the user's provided image, generate a report with the following structure and headings:\n\nDescription\nWrite a comprehensive, single-paragraph description of the entire image. Capture the subject, setting, style, and overall feeling of the scene.\n\nStyle Analysis\n\nCore Subject: Identify the main person, object, or focus of the image.\n\nSetting: Describe the background and environment of the subject.\n\nMedium: Specify the artistic medium (e.g., Commercial product photography, 3D render, oil painting, analog film photo).\n\nLighting: Describe the quality and source of the light (e.g., golden hour, studio lighting, neon glow).\n\nMood: Describe the overall feeling or atmosphere (e.g., serene, energetic, futuristic, nostalgic).\n\nComposition: Describe the framing and camera angle (e.g., centered, eye-level, low-angle, top-down).\n\nColor Palette: List the dominant colors and overall color scheme.\n\nText Overlay\nList and describe each distinct piece of text found in the image. If there is no text, simply write \"None.\"\n\nText 1\n\nText: Identify the exact text.\n\nFont: Describe the font style.\n\nEffect: Describe any visual effects on the font. If none, write \"None.\"\n\nColor: Identify the color of the text.\n\nPlacement: Describe where the text is located (e.g., center, bottom-left).\n\n(Repeat the \"Text #\" section for every additional piece of text in the image.)",
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "GPT-4O-MINI"
},
"options": [],
"resource": "image",
"imageUrls": "={{ $json.Picture[0].url }}",
"operation": "analyze"
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.8
},
{
"id": "ece7ceee-ef5a-403b-a0bd-e5ab77be62cf",
"name": "OpenAI Chat Engine",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
740,
390
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini"
},
"options": []
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "44a27005-e034-4fa0-a071-09b1f8915bab",
"name": "Build Media Container",
"type": "n8n-nodes-base.httpRequest",
"position": [
700,
610
],
"parameters": {
"url": "https://graph.facebook.com/v18.0/[YOUR_ID]/media",
"method": "POST",
"options": [],
"jsonBody": "={\n  \"image_url\": \"\",\n  \"caption\": \"Your caption text here #hashtag\",\n  \"access_token\": \"[CONFIGURE_YOUR_TOKEN]\"\n}",
"sendBody": true,
"specifyBody": "json"
},
"typeVersion": 4.2
},
{
"id": "0a495e3b-649f-44ae-b10c-874d605db264",
"name": "Release Media Post",
"type": "n8n-nodes-base.httpRequest",
"position": [
930,
600
],
"parameters": {
"url": "https://graph.facebook.com/v18.0/[YOUR_ID]/media_publish",
"method": "POST",
"options": [],
"jsonBody": "={\n  \"creation_id\": \"{{ $('Build Media Container').item.json.id }}\",\n  \"access_token\": \"[CONFIGURE_YOUR_TOKEN]\"\n}",
"sendBody": true,
"specifyBody": "json"
},
"typeVersion": 4.2
},
{
"id": "de7de152-7cc6-4c7d-ab62-0a0b9dc7fde4",
"name": "Fetch Source Image",
"type": "n8n-nodes-base.airtable",
"position": [
260,
130
],
"parameters": {
"id": "={{ $json.query.recordId }}",
"base": {
"__rl": true,
"mode": "list",
"value": "appwDeP1gnsXXthZ6",
"cachedResultUrl": "https://airtable.com/appwDeP1gnsXXthZ6",
"cachedResultName": "Nano Image Gen IG posting"
},
"table": {
"__rl": true,
"mode": "list",
"value": "tblCzppnhEo5uVeTq",
"cachedResultUrl": "https://airtable.com/appwDeP1gnsXXthZ6/tblCzppnhEo5uVeTq",
"cachedResultName": "NannoB"
},
"options": []
},
"credentials": {
"airtableTokenApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2.1
},
{
"id": "a921857e-6b50-4ae9-a4a7-3eb41bd10e59",
"name": "Retrieve Pending Rows",
"type": "n8n-nodes-base.airtable",
"position": [
760,
140
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "appwDeP1gnsXXthZ6",
"cachedResultUrl": "https://airtable.com/appwDeP1gnsXXthZ6",
"cachedResultName": "Nano Image Gen IG posting"
},
"table": {
"__rl": true,
"mode": "list",
"value": "tblCzppnhEo5uVeTq",
"cachedResultUrl": "https://airtable.com/appwDeP1gnsXXthZ6/tblCzppnhEo5uVeTq",
"cachedResultName": "NannoB"
},
"options": {
"fields": [
"ID",
"Status",
"Setting",
"Composition",
"Lighting",
"Style",
"Atmosphere",
"Color Palette",
"Text Overlay",
"Post Description"
]
},
"operation": "search",
"filterByFormula": "{Status} = \"Create\""
},
"credentials": {
"airtableTokenApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2.1
},
{
"id": "9f2ca879-097e-4a8d-8eaa-d07deec0e00a",
"name": "Refine Edit Prompt",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
500,
380
],
"parameters": {
"text": "=Prompt guidelines for the edited image:\n\nPost Description: {{ $json['Post Description'] }}\nComposition: {{ $json.Composition }}\nLighting: {{ $json.Lighting }}\nStyle: {{ $json.Style }}\nAtmosphere: {{ $json.Atmosphere }}\nColor Palette: {{ $json['Color Palette'] }}\nText Overlay: {{ $json['Text Overlay'] }}",
"batching": [],
"messages": {
"messageValues": [
{
"message": "=Your task is to generate an image editing prompt for AI-powered image modification. You will receive the Base Image description from your system configuration. The user will then supply editing specifications that detail their desired changes across these elements: Post Description, Composition, Lighting, Style, Atmosphere, Color Palette, and Text Overlay. Some aspects may remain unchanged from the base image while others will be modified.\nUsing these editing specifications, construct an image modification prompt that maintains consistency with the original image description's formatting and structure, while incorporating the requested changes for Instagram-optimized content.\nYour response must contain exclusively the revised image editing prompt. Include no explanatory text, introductions, or concluding statements.\nBase Image description: {{ $('Inspect Image Content').item.json.content }}"
}
]
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "8c99af55-d9f1-4e88-9d15-bc57f48eb40c",
"name": "Generate Banana Image",
"type": "n8n-nodes-base.httpRequest",
"onError": "continueErrorOutput",
"position": [
250,
400
],
"parameters": {
"url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent",
"method": "POST",
"options": {
"batching": {
"batch": {
"batchSize": 1,
"batchInterval": 5000
}
}
},
"jsonBody": "={\n  \"contents\": [\n    {\n      \"parts\": [\n        {\n          \"text\": {{ JSON.stringify(\n            'Original Image Prompt: ' +\n            $('Inspect Image Content').item.json.content+\n            ' Requested Edit Prompt: ' +\n            $json.text\n          ) }}\n        },\n        {\n          \"inline_data\": {\n            \"mime_type\": \"image/jpeg\",\n            \"data\": \"{{ $('Fetch Source Image').item.json['Nano Image'][0].url }}\"\n          }\n        }\n      ]\n    }\n  ],\n  \"generationConfig\": {\n    \"temperature\": 0.7,\n    \"maxOutputTokens\": 1000\n  }\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2,
"alwaysOutputData": false
}
],
"active": true,
"pinData": [],
"settings": {
"executionOrder": "v1"
},
"versionId": null,
"connections": {
"Incoming Webhook Trigger": {
"main": [
[
{
"node": "Fetch Source Image",
"type": "main",
"index": 0
}
]
]
},
"Retrieve Pending Rows": {
"main": [
[
{
"node": "Refine Edit Prompt",
"type": "main",
"index": 0
}
]
]
},
"Fetch Source Image": {
"main": [
[
{
"node": "Inspect Image Content",
"type": "main",
"index": 0
}
]
]
},
"Inspect Image Content": {
"main": [
[
{
"node": "Retrieve Pending Rows",
"type": "main",
"index": 0
}
]
]
},
"Release Media Post": {
"main": [
[
{
"node": "Mark Status Complete",
"type": "main",
"index": 0
}
]
]
},
"Airtable Attachment Upload": {
"main": [
[]
]
},
"OpenAI Chat Engine": {
"ai_languageModel": [
[
{
"node": "Refine Edit Prompt",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Refine Edit Prompt": {
"main": [
[
{
"node": "Generate Banana Image",
"type": "main",
"index": 0
}
]
]
},
"Build Media Container": {
"main": [
[
{
"node": "Release Media Post",
"type": "main",
"index": 0
}
]
]
},
"Generate Banana Image": {
"main": [
[
{
"node": "Airtable Attachment Upload",
"type": "main",
"index": 0
},
{
"node": "Build Media Container",
"type": "main",
"index": 0
}
],
[
{
"node": "Mark Status Failed",
"type": "main",
"index": 0
}
]
]
}
}
}